AIBullisharXiv – CS AI · 10h ago7/10
🧠
LiteMedCoT-VL: Parameter-Efficient Adaptation for Medical Visual Question Answering
Researchers introduce LiteMedCoT-VL, a technique that transfers chain-of-thought reasoning from large language models to compact 2B parameter models for medical visual question answering, achieving 64.9% accuracy on the PMC-VQA benchmark without relying on image captions. The breakthrough demonstrates that smaller models enhanced with reasoning distillation can match or exceed the performance of larger models, enabling deployment of sophisticated medical AI on resource-constrained clinical devices.